Smartwatch app accurately detects atrial fibrillation
The 12-lead electrocardiogram, a noninvasive device that shows the heart’s electrical activity, is considered the gold standard for diagnosing patients with the cardiac rhythm disorder atrial fibrillation.
However, the Cleveland Clinic has demonstrated that a smartwatch wristband and app—cleared by the U.S. Food and Drug Administration in November—can accurately display the heart’s electrical activity and notify patients with AFib if their heart is beating normally or not.
AliveCor’s commercially available Kardia Band is paired with an app that uses an algorithm to instantaneously inform the wearer of the single-lead ECG if their heart rhythm is normal, indicative of AFib or undetermined.
In a blinded, prospective study of 100 patients, the wearable device detected AFib with 93 percent sensitivity and 84 percent specificity compared with the 12-lead ECG used in clinic. However, when an electrophysiologist also interpreted the data, the accuracy was improved even further to 99 percent sensitivity and 83 percent specificity. Sensitivity is defined as the ability to correctly identify patients with the disease, and specificity is defined as how accurately it identifies those without the disease.
“Out of the box, the smartwatch band and its algorithm were very good at identifying AFib, but when coupled with a physician’s interpretation of the recording (as it should be used), it became even more clinically useful,” says Joseph Bumgarner, MD, an electrophysiology fellow at the Cleveland Clinic and the lead author of the study.
Bumgarner asserts that although the Kardia Band only has a single lead compared to the 12-lead ECG, the smartwatch can diagnose AFib successfully. “A patient concerned about having AFib may purchase it and make recordings that they can share with their physician—and, together by looking at the data, can make a diagnosis,” he adds. “The physician oversight really makes it a powerful tool.”
According to Bumgarner, while AliveCor provided smartwatches to the Cleveland Clinic, the vendor was not involved in the design, implementation, data analysis or interpretation of the study’s results.
Eric Topol, MD, a practicing cardiologist and director of the Scripps Translational Science Institute, contends that the results of the study are not at all surprising.
“The Kardia Band deep learning algorithm is quite accurate in diagnosing AFib, which is how it was approved by the FDA,” says Topol, who is also executive vice president and professor of molecular medicine at The Scripps Research Institute. “This just adds another small study of 100 patients of support.”
Bumgarner will present the results of the study on March 11 at the American College of Cardiology's 67th Annual Scientific Session in Orlando, Fla.
Although the Cleveland Clinic did not measure cost in its study, Bumgarner believes there could be potential cost savings in the future associated with using the device, provided it is validated in clinical trials.
“There were a significant number of patients—about 8 percent—who on the day of their procedure were found to have a normal heart rhythm (as determined by the smartwatch and validated by the ECG) and did not require a procedure,” he observes. “In the future, this technology may help screen patients prior to presentation for elective procedures and avoid scheduling ones that are unnecessary.”
Going forward, the Cleveland Clinic is planning to conduct a study to evaluate potential cost savings in an outpatient setting in which participants will use the Kardia Band at home. “AliveCor has designed a secure, cloud-based platform where all these ECG tracings can be uploaded so patients and physicians can view them,” concludes Bumgarner. “We’re testing that platform and how it might integrate into a busy cardiology practice.”